Deep Learning for Tabular Data: A Bag of Tricks | ODSC 2020
Jason McGhee, Senior Machine Learning Engineer at DataRobot, has been spending time applying deep learning and neural networks to tabular data. Although the deep learning technique can prove challenging, his research supports how valuable it is when using tabular datasets. In this video (adapted from his presentation at ODSC Boston 2020), Jason shares some important techniques for implementing deep learning when learning heterogenous tabular data. Learn more about Jason’s findings and ask him questions at his DataRobot Community post: https://community.datarobot.com/t5/ai-ml-general-blog/deep-learning-for-tabular-data-a-bag-of-tricks/ba-p/4593
Table of Contents
Motivation: 0:15
Impute missing values: 1:37
Prepare categoricals, text, and numerics: 2:49, 3:10, 3:31
Properly validate: 3:54
Establish a benchmark: 5:24
Start with a low capacity network: 6:10
Determine output activation and loss function for classification and regression: 7:17, 8:26
Determine hidden activation: 9:46
Choose batch size: 10:57
Build learning rate schedule: 12:02
Determine number of epochs: 14:35
Track and interpret regression predictions: 15:30
Track metric and/or loss: 16:09
Track and interpret classification predictions: 16:45
Benchmark the network: 17:11
Dealing with discontinuities: 18:16
Tuning the network: 19:31
Handing overfitting vs. underfitting: 20:41
All tricks in one place: 21:35
Music for this video: https://www.bensound.com.
Stay connected with DataRobot!
Blog: https://blog.datarobot.com/
Community: https://community.datarobot.com/
Twitter: https://twitter.com/DataRobot
LinkedIn: hhttps://www.linkedin.com/company/datarobot/
Facebook: https://www.facebook.com/datarobotinc
Instagram: https://www.instagram.com/datarobot/
Видео Deep Learning for Tabular Data: A Bag of Tricks | ODSC 2020 канала DataRobot
Table of Contents
Motivation: 0:15
Impute missing values: 1:37
Prepare categoricals, text, and numerics: 2:49, 3:10, 3:31
Properly validate: 3:54
Establish a benchmark: 5:24
Start with a low capacity network: 6:10
Determine output activation and loss function for classification and regression: 7:17, 8:26
Determine hidden activation: 9:46
Choose batch size: 10:57
Build learning rate schedule: 12:02
Determine number of epochs: 14:35
Track and interpret regression predictions: 15:30
Track metric and/or loss: 16:09
Track and interpret classification predictions: 16:45
Benchmark the network: 17:11
Dealing with discontinuities: 18:16
Tuning the network: 19:31
Handing overfitting vs. underfitting: 20:41
All tricks in one place: 21:35
Music for this video: https://www.bensound.com.
Stay connected with DataRobot!
Blog: https://blog.datarobot.com/
Community: https://community.datarobot.com/
Twitter: https://twitter.com/DataRobot
LinkedIn: hhttps://www.linkedin.com/company/datarobot/
Facebook: https://www.facebook.com/datarobotinc
Instagram: https://www.instagram.com/datarobot/
Видео Deep Learning for Tabular Data: A Bag of Tricks | ODSC 2020 канала DataRobot
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Deep Learning for tabular data - #DevFestVeneto19](https://i.ytimg.com/vi/nQgUt_uADSE/default.jpg)
![Attention in Neural Networks](https://i.ytimg.com/vi/W2rWgXJBZhU/default.jpg)
![But what is a neural network? | Chapter 1, Deep learning](https://i.ytimg.com/vi/aircAruvnKk/default.jpg)
![Inside a Neural Network - Computerphile](https://i.ytimg.com/vi/BFdMrDOx_CM/default.jpg)
![How to Choose an NVIDIA GPU for Deep Learning in 2021: Quadro, Ampere, GeForce Compared](https://i.ytimg.com/vi/pWzlL51oqRo/default.jpg)
![How Well Can an AI Learn Physics? ⚛](https://i.ytimg.com/vi/2Bw5f4vYL98/default.jpg)
![What REALLY is Data Science? Told by a Data Scientist](https://i.ytimg.com/vi/xC-c7E5PK0Y/default.jpg)
![How to Train Your Models in the Cloud](https://i.ytimg.com/vi/Bgwujw-yom8/default.jpg)
![Talks # 4: Sebastien Fischman - Pytorch-TabNet: Beating XGBoost on Tabular Data Using Deep Learning](https://i.ytimg.com/vi/ysBaZO8YmX8/default.jpg)
![Deep portfolio: using neural networks for portfolio construction - Anant Gupta](https://i.ytimg.com/vi/7LOb9kk6U_M/default.jpg)
![Deep Learning - Computerphile](https://i.ytimg.com/vi/l42lr8AlrHk/default.jpg)
![[AI] How to normalize and un-normalize a tabular data for neural networks?](https://i.ytimg.com/vi/Tu8Dl3zorgg/default.jpg)
![[PseudoCon 2020] Tabular Data를 위한 딥러닝 모델 TabNet & 앙상블](https://i.ytimg.com/vi/zYnjzdbH3R8/default.jpg)
![Why Does Batch Norm Work? (C2W3L06)](https://i.ytimg.com/vi/nUUqwaxLnWs/default.jpg)
![Deep Learning State of the Art (2020)](https://i.ytimg.com/vi/0VH1Lim8gL8/default.jpg)
![Stock Price Prediction Using Python & Machine Learning](https://i.ytimg.com/vi/QIUxPv5PJOY/default.jpg)
![Deep Learning Frameworks 2019](https://i.ytimg.com/vi/SJldOOs4vB8/default.jpg)
![An Introduction to Graph Neural Networks: Models and Applications](https://i.ytimg.com/vi/zCEYiCxrL_0/default.jpg)
![Hilary Mason: The Future of AI and Machine Learning | Keynote Address | ODSC East 2019](https://i.ytimg.com/vi/FXG1dOM_Orc/default.jpg)
![Deep Learning for Tabular Data – Mr. Yam Peleg](https://i.ytimg.com/vi/3-W9wkZrZL8/default.jpg)